Chenguang Ma
12 papers · 2014–2026 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (27) 🏃 Academic Marathon · Half 🌍 Conference Polyglot · Bronze ⚡ Prolific Year · Productive
💎
Century Club · Bronze
🗃️
Keyword Collector
(67)
Top co-authors
Research topics
Computer Vision
(8)
Artificial Intelligence
(7)
Deep Learning
(7)
Core AI · Artificial Intelligence
(7)
Generation
(5)
Models
(5)
Machine Learning
(3)
Processing
(3)
Analysis
(2)
Application Areas
(2)
Core AI · Computer Vision
(2)
Interdisciplinary
(1)
Natural Language Processing
(1)
Applications
(1)
Architectures
(1)
Keywords
diffusion model
(4)
human animation
(2)
portrait generation
(2)
audio-driven animation
(2)
multimodal learning
(2)
vision-language model
(2)
identity preservation
(2)
audio-driven generation
(2)
image generation
(2)
knowledge distillation
(1)
3d face model
(1)
video generation
(1)
latent space
(1)
generative adversarial network
(1)
3d reconstruction
(1)
state space model
(1)
parameter efficiency
(1)
computational efficiency
(1)
edge deployment
(1)
gesture synthesis
(1)
Papers
EchoMimicV3: 1.3B Parameters Are All You Need for Unified Multi-Modal and Multi-Task Human Animation
AAAI 2026
EmojiDiff: Advanced Facial Expression Control with High Identity Preservation in Portrait Generation
WACV 2026
Exposing and Evaluating Hallucinations for GUI Grounding
CVPR 2026
GroupPortrait: Multi-ID Portrait Generation with High Identity Preservation and Fine-Grained Control
WACV 2026
QuietPrune: Query-Guided Early Token Pruning for Vision-Language Models
CVPR 2026
SPEED-Q: Staged Processing with Enhanced Distillation Towards Efficient Low-Bit On-Device VLM Quantization
AAAI 2026
EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditions
AAAI 2025
EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation
CVPR 2025
Efficient Video Face Enhancement with Enhanced Spatial-Temporal Consistency
CVPR 2025
SpeedUpNet: A Plug-and-Play Adapter Network for Accelerating Text-to-Image Diffusion Models
ECCV 2024
FaceVerse: A Fine-Grained and Detail-Controllable 3D Face Morphable Model From a Hybrid Dataset
CVPR 2022
Transparent Object Reconstruction via Coded Transport of Intensity
CVPR 2014